NOHARM study finds medical AI often matches or beats general practitioners

jonc101x · x · 2026-07-27

In the NOHARM study, frontier and medical-specific AI systems handled complex clinical consultations remarkably well, often matching or outperforming general practitioners — even when the doctors had references or AI assistance themselves.

The thread argues that the real risk is not just confidently wrong answers, but omission: reassuring users with "nothing to do" when a dangerous condition actually needs a workup.

Related event: AI Health Advisors: Matching Doctors but Needing Safety Guardrails(16 posts)→

Original post →

More from Safety

Safety channel →